scholarly journals Connectome-based individual prediction of cognitive behaviors via the graph propagation network reveals directed brain network topology

2021 ◽  
Author(s):  
Dongya Wu ◽  
Xin Li ◽  
Jun Feng
Keyword(s):  
Neural Network ◽  
Information Flow ◽  
Network Topology ◽  
Cognitive Behaviors ◽  
Human Behaviors ◽  
Brain Connectome ◽  
The Individual ◽  
Propagation Network ◽  
Graph Propagation ◽  
The Brain

AbstractThe brain connectome supports the information flow underlying human cognitions and should reflect the individual variability in human cognitive behaviors. Various studies have utilized the brain connectome to predict individual differences in human behaviors. However, traditional studies viewed the brain connectome feature as a vector of one dimension, a method which neglects topological structures of the brain connectome. To utilize topological properties of the brain connectome, we proposed that graph neural network which combines graph theory and neural network can be adopted. Different from previous node-driven graph neural networks that parameterize on the node feature transformation, we designed an edge-driven graph neural network named graph propagation network that parameterizes on the information propagation within the brain connectome. We compared various models in predicting the individual total cognition based on the resting-state functional connectome. The edge-driven graph propagation network showed the highest prediction accuracy and outperformed the node-driven graph neural network and traditional partial least square regression. The graph propagation network also revealed a directed network topology encoding the information flow, indicating that the high-level association cortices are responsible for the information integration underlying the total cognition. These results suggest that the edge-driven graph propagation network can better explore the topological structure of the brain connectome and can serve as a new method to associate the brain connectome and human behaviors.

scholarly journals Multi-Hops Functional Connectivity Improves Individual Prediction of Fusiform Face Activation via a Graph Neural Network

2021 ◽  
Vol 14 ◽  
Author(s):  
Dongya Wu ◽  
Xin Li ◽  
Jun Feng
Keyword(s):  
Neural Network ◽  
Functional Connectivity ◽  
Brain Connectivity ◽  
Face Area ◽  
The Face ◽  
The Individual ◽  
The Right ◽  
And Function ◽  
The Relationship ◽  
The Brain

Brain connectivity plays an important role in determining the brain region’s function. Previous researchers proposed that the brain region’s function is characterized by that region’s input and output connectivity profiles. Following this proposal, numerous studies have investigated the relationship between connectivity and function. However, this proposal only utilizes direct connectivity profiles and thus is deficient in explaining individual differences in the brain region’s function. To overcome this problem, we proposed that a brain region’s function is characterized by that region’s multi-hops connectivity profile. To test this proposal, we used multi-hops functional connectivity to predict the individual face activation of the right fusiform face area (rFFA) via a multi-layer graph neural network and showed that the prediction performance is essentially improved. Results also indicated that the two-layer graph neural network is the best in characterizing rFFA’s face activation and revealed a hierarchical network for the face processing of rFFA.

Self-Organization Processes in Chaotic Neural Networks Under External Periodic Force

1997 ◽  
Vol 07 (08) ◽  
pp. 1887-1895 ◽  
Author(s):  
Vladimir E. Bondarenko
Keyword(s):  
Neural Network ◽  
External Force ◽  
Self Organization ◽  
Largest Lyapunov Exponent ◽  
Periodic Force ◽  
Chaotic Neural Networks ◽  
The Neural Network ◽  
Quantitative Characteristics ◽  
The Individual ◽  
The Brain

Self-organization processes in an analog asymmetric neural network with time delay and under an external sinusoidal force are considered. Quantitative characteristics of the neuron outputs (spectrum, correlation dimension, largest Lyapunov exponent, Shannon entropy, normalized and renormalized Shannon entropies) are studied in dependence on the frequency and amplitude of the external force. It is shown that the external sinusoidal force allows the control of the degree of chaos and produces transitions "order–chaos", "chaos–order" and "chaos–chaos" with different quantitative characteristics. Information processing both by the individual neurons and by the neural network as a system is discussed. Chaotic neural network under an external force is considered as a qualitative model of the infra-frequencies action on the brain.

scholarly journals Formation of neural networks with structural and functional features consistent with small-world network topology on surface-grafted polymer particles

2019 ◽  
Vol 6 (10) ◽  
pp. 191086 ◽  
Author(s):  
Vibeke Devold Valderhaug ◽  
Wilhelm Robert Glomm ◽  
Eugenia Mariana Sandru ◽  
Masahiro Yasuda ◽  
Axel Sandvig ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Topology ◽  
Small World ◽  
Network Activity ◽  
Small World Network ◽  
Grafted Polymer ◽  
Functional Features ◽  
The Brain

In vitro electrophysiological investigation of neural activity at a network level holds tremendous potential for elucidating underlying features of brain function (and dysfunction). In standard neural network modelling systems, however, the fundamental three-dimensional (3D) character of the brain is a largely disregarded feature. This widely applied neuroscientific strategy affects several aspects of the structure–function relationships of the resulting networks, altering network connectivity and topology, ultimately reducing the translatability of the results obtained. As these model systems increase in popularity, it becomes imperative that they capture, as accurately as possible, fundamental features of neural networks in the brain, such as small-worldness. In this report, we combine in vitro neural cell culture with a biologically compatible scaffolding substrate, surface-grafted polymer particles (PPs), to develop neural networks with 3D topology. Furthermore, we investigate their electrophysiological network activity through the use of 3D multielectrode arrays. The resulting neural network activity shows emergent behaviour consistent with maturing neural networks capable of performing computations, i.e. activity patterns suggestive of both information segregation (desynchronized single spikes and local bursts) and information integration (network spikes). Importantly, we demonstrate that the resulting PP-structured neural networks show both structural and functional features consistent with small-world network topology.

scholarly journals Multi-hops functional connectivity improves individual prediction of fusiform face activation via a graph neural network

2020 ◽  
Author(s):  
Dongya Wu ◽  
Xin Li ◽  
Jun Feng
Keyword(s):  
Neural Network ◽  
Functional Connectivity ◽  
Brain Connectivity ◽  
Face Area ◽  
The Face ◽  
The Individual ◽  
The Right ◽  
And Function ◽  
The Relationship ◽  
The Brain

AbstractBrain connectivity plays an important role in determining the brain region’s function. Previous researchers proposed that the brain region’s function is characterized by that region’s input and output connectivity profiles. Following this proposal, numerous studies have investigated the relationship between connectivity and function. However, based on a preliminary analysis, this proposal is deficient in explaining individual differences in the brain region’s function. To overcome this problem, we proposed that a brain region’s function is characterized by that region’s multi-hops connectivity profile. To test this proposal, we used multi-hops functional connectivity to predict the individual face response of the right fusiform face area (rFFA) via a multi-layers graph neural network and showed that the prediction performance is essentially improved. Results also indicated that the 2-layers graph neural network is the best in characterizing rFFA’s face response and revealed a hierarchical network for the face processing of rFFA.

scholarly journals Epilepsy: The Quintessential Pathology of Consciousness

2011 ◽  
Vol 24 (1) ◽  
pp. 3-10 ◽  
Author(s):  
Andrea Eugenio Cavanna ◽  
Fizzah Ali
Keyword(s):  
Neural Network ◽  
Subjective Experience ◽  
Experimental Models ◽  
Partial Seizures ◽  
Impaired Consciousness ◽  
Complex Partial Seizures ◽  
Targeted Treatments ◽  
Brain Correlates ◽  
The Individual ◽  
The Brain

Alterations in consciousness are central to epileptic manifestations, and involve changes in both the level of awareness and subjective content of consciousness. Generalised seizures are characterised by minimal responsiveness and subjective experience whereas simple and complex partial seizures demonstrate more selective disturbances. Despite variations in ictal origin, behaviour and electrophysiology, the individual seizure types share common neuroanatomical foundations generating impaired consciousness. This article provides a description of the phenomenology of ictal consciousness and reviews the underlying shared neural network, dubbed the 'consciousness system', which overlaps with the 'default mode' network. In addition, clinical and experimental models for the study of the brain correlates of ictal alterations of consciousness are discussed. It is argued that further investigation into both human and animal models will permit greater understanding of brain mechanisms and associated behavioural consequences, possibly leading to the development of new targeted treatments.

scholarly journals Performance Analysis of EEG Signals using Conventional and Hybrid Artificial Neural Network

2019 ◽  
Vol 8 (4S2) ◽  
pp. 569-576
Keyword(s):  
Neural Network ◽  
Motor Neurons ◽  
Electrode System ◽  
Eeg Signals ◽  
Feed Forward Neural Network ◽  
Time Duration ◽  
Feed Forward ◽  
Real World Problem ◽  
The Individual ◽  
The Brain

Brain Computer Interface (BCI) using Electrooencephalogram (EEG) is one of the versatile tools to measure the brain thoughts and convert them to operate the external devices in the deficiency of biological controls. These techniques are used to develop the rehabilitative devices for the individual person who affected with locked in syndrome (LIS). The main reason for LIS is due to death of motor neurons. To overcome the real world problem we conduct our experiment with eight normal patients for four tasks using three electrode system and ADI T26 bio amplifier with Lab chart. Four task signals are applied to statistical method to retrieve the twenty two features and trained with the feed forward neural network (FFNN) and feed forward neural network with wolf Grey optimization algorithm (FFNNWGOA) to see network model which was more perfectly supported to identify the tasks. The study showed that statistical features through feed forward neural network with grey wolf optimized algorithm classifier produced maximum performances of 94.06% compared to other feed forward neural network classifier model and also we identified that optimized features demonstrated maximum performances in minimum time duration during training in all the following twenty trials.

Fit Vs Faint: Assessing Work Causation in “Idiopathic Fall” Cases

2014 ◽  
Vol 19 (5) ◽  
pp. 3-12
Author(s):  
Lorne Direnfeld ◽  
David B. Torrey ◽  
Jim Black ◽  
LuAnn Haley ◽  
Christopher R. Brigham
Keyword(s):  
Blood Flow ◽  
Electrical Activity ◽  
Loss Of Consciousness ◽  
Brain Electrical Activity ◽  
Medical Terminology ◽  
Scientific Analysis ◽  
Medical Causation ◽  
The Individual ◽  
The Brain ◽  
Current Science

Abstract When an individual falls due to a nonwork-related episode of dizziness, hits their head and sustains injury, do workers’ compensation laws consider such injuries to be compensable? Bearing in mind that each state makes its own laws, the answer depends on what caused the loss of consciousness, and the second asks specifically what happened in the fall that caused the injury? The first question speaks to medical causation, which applies scientific analysis to determine the cause of the problem. The second question addresses legal causation: Under what factual circumstances are injuries of this type potentially covered under the law? Much nuance attends this analysis. The authors discuss idiopathic falls, which in this context means “unique to the individual” as opposed to “of unknown cause,” which is the familiar medical terminology. The article presents three detailed case studies that describe falls that had their genesis in episodes of loss of consciousness, followed by analyses by lawyer or judge authors who address the issue of compensability, including three scenarios from Arizona, California, and Pennsylvania. A medical (scientific) analysis must be thorough and must determine the facts regarding the fall and what occurred: Was the fall due to a fit (eg, a seizure with loss of consciousness attributable to anormal brain electrical activity) or a faint (eg, loss of consciousness attributable to a decrease in blood flow to the brain? The evaluator should be able to fully explain the basis for the conclusions, including references to current science.

Comparison of an Artificial Neural Network and a Multiple Linear Regression in Predicting the Heat of Combustion of Diesel Fuel Based on Hydrocarbon Groups

2020 ◽  
Vol 71 (6) ◽  
pp. 66-74
Author(s):  
Younis M. Younis ◽  
Salman H. Abbas ◽  
Farqad T. Najim ◽  
Firas Hashim Kamar ◽  
Gheorghe Nechifor
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Diesel Fuel ◽  
Back Propagation ◽  
Second Step ◽  
Heating Value ◽  
Network Training ◽  
Marquardt Algorithm ◽  
Levenberg Marquardt ◽  
Propagation Network

A comparison between artificial neural network (ANN) and multiple linear regression (MLR) models was employed to predict the heat of combustion, and the gross and net heat values, of a diesel fuel engine, based on the chemical composition of the diesel fuel. One hundred and fifty samples of Iraqi diesel provided data from chromatographic analysis. Eight parameters were applied as inputs in order to predict the gross and net heat combustion of the diesel fuel. A trial-and-error method was used to determine the shape of the individual ANN. The results showed that the prediction accuracy of the ANN model was greater than that of the MLR model in predicting the gross heat value. The best neural network for predicting the gross heating value was a back-propagation network (8-8-1), using the Levenberg�Marquardt algorithm for the second step of network training. R = 0.98502 for the test data. In the same way, the best neural network for predicting the net heating value was a back-propagation network (8-5-1), using the Levenberg�Marquardt algorithm for the second step of network training. R = 0.95112 for the test data.

Individual Uniqueness in the Neonatal Functional Connectome

2021 ◽  
Author(s):  
Qiushi Wang ◽  
Yuehua Xu ◽  
Tengda Zhao ◽  
Zhilei Xu ◽  
Yong He ◽  
...  
Keyword(s):  
Individual Differences ◽  
Individual Identification ◽  
Imaging Data ◽  
Functional Connectome ◽  
Middle Range ◽  
Human Connectome Project ◽  
The Individual ◽  
And Behavior ◽  
Identification Analysis ◽  
The Brain

Abstract The functional connectome is highly distinctive in adults and adolescents, underlying individual differences in cognition and behavior. However, it remains unknown whether the individual uniqueness of the functional connectome is present in neonates, who are far from mature. Here, we utilized the multiband resting-state functional magnetic resonance imaging data of 40 healthy neonates from the Developing Human Connectome Project and a split-half analysis approach to characterize the uniqueness of the functional connectome in the neonatal brain. Through functional connectome-based individual identification analysis, we found that all the neonates were correctly identified, with the most discriminative regions predominantly confined to the higher-order cortices (e.g., prefrontal and parietal regions). The connectivities with the highest contributions to individual uniqueness were primarily located between different functional systems, and the short- (0–30 mm) and middle-range (30–60 mm) connectivities were more distinctive than the long-range (>60 mm) connectivities. Interestingly, we found that functional data with a scanning length longer than 3.5 min were able to capture the individual uniqueness in the functional connectome. Our results highlight that individual uniqueness is present in the functional connectome of neonates and provide insights into the brain mechanisms underlying individual differences in cognition and behavior later in life.

Sign in / Sign up

Export Citation Format

Share Document